{"id":13440762,"url":"https://github.com/ai4ce/V2X-Sim","last_synced_at":"2025-03-20T10:32:22.871Z","repository":{"id":44366090,"uuid":"400240444","full_name":"ai4ce/V2X-Sim","owner":"ai4ce","description":"[RA-L2022] V2X-Sim Dataset and Benchmark","archived":false,"fork":false,"pushed_at":"2023-09-15T20:27:23.000Z","size":393269,"stargazers_count":108,"open_issues_count":5,"forks_count":15,"subscribers_count":5,"default_branch":"main","last_synced_at":"2024-07-12T11:11:24.520Z","etag":null,"topics":["benchmark","collaborative-perception","computer-vision","dataset","deep-learning","machine-learning","multi-robot-systems","pytorch","simulation","v2x","vehicle-to-everything"],"latest_commit_sha":null,"homepage":"https://ai4ce.github.io/V2X-Sim","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ai4ce.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2021-08-26T16:45:29.000Z","updated_at":"2024-07-12T07:10:31.000Z","dependencies_parsed_at":"2024-01-16T02:45:30.389Z","dependency_job_id":"6f16a5f9-87c2-4ec0-88f3-762cb3b5f032","html_url":"https://github.com/ai4ce/V2X-Sim","commit_stats":{"total_commits":31,"total_committers":7,"mean_commits":4.428571428571429,"dds":0.7096774193548387,"last_synced_commit":"37150e07f0b83d764cd22596b9e763849640a75a"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ai4ce%2FV2X-Sim","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ai4ce%2FV2X-Sim/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ai4ce%2FV2X-Sim/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ai4ce%2FV2X-Sim/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ai4ce","download_url":"https://codeload.github.com/ai4ce/V2X-Sim/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":213299351,"owners_count":15566608,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["benchmark","collaborative-perception","computer-vision","dataset","deep-learning","machine-learning","multi-robot-systems","pytorch","simulation","v2x","vehicle-to-everything"],"created_at":"2024-07-31T03:01:25.920Z","updated_at":"2025-03-20T10:32:22.826Z","avatar_url":"https://github.com/ai4ce.png","language":null,"funding_links":[],"categories":["Others"],"sub_categories":[],"readme":"# V2X-Sim: Multi-Agent Collaborative Perception Dataset and Benchmark for Autonomous Driving [RA-L 2022]\n\n[Yiming Li](https://scholar.google.com/citations?user=i_aajNoAAAAJ), [Dekun Ma](https://dekun.me), [Ziyan An](https://ziyanan.github.io/), [Zixun Wang](), [Yiqi Zhong](https://www.linkedin.com/in/yiqi-zhong-078548129), [Siheng Chen](https://scholar.google.com/citations?user=W_Q33RMAAAAJ\u0026hl=en), [Chen Feng](https://scholar.google.com/citations?user=YeG8ZM0AAAAJ)\n\n**\"A comprehensive multi-agent multi-modal multi-task 3D perception dataset for autonomous driving.\"**\n\n[![arXiv](https://img.shields.io/badge/Website-V2X--Sim-blue)](https://ai4ce.github.io/V2X-Sim/) \n![PyTorch](https://img.shields.io/badge/PyTorch-%23EE4C2C.svg?logo=PyTorch\u0026logoColor=white)\n[![GitLab issues total](https://badgen.net/github/issues/ai4ce/V2X-Sim)](https://gitlab.com/ai4ce/V2X-Sim/issues)\n[![GitHub stars](https://img.shields.io/github/stars/ai4ce/V2X-Sim.svg?style=social\u0026label=Star\u0026maxAge=2592000)](https://GitHub.com/ai4ce/V2X-Sim/stargazers/)\n\u003cdiv align=\"center\"\u003e\n    \u003cimg src=\"https://s2.loli.net/2022/06/15/cbs6hS2NHT7pDPL.png\" height=\"300\"\u003e\n\u003c/div\u003e\n\u003cbr\u003e\n\n## News\n**[2022-07]**  Our paper is available at [arxiv](https://arxiv.org/pdf/2202.08449.pdf).\n\n**[2022-06]**  🔥 V2X-Sim is accepted at **IEEE Robotics and Automation Letters (RA-L)**.\n\n## Abstract\n\nVehicle-to-everything (V2X) communication techniques enable the collaboration between a vehicle and any other\nentity in its surrounding, which could fundamentally improve\nthe perception system for autonomous driving. However, the\nlack of a public dataset significantly restricts the research\nprogress of collaborative perception. To fill this gap, we present\nV2X-Sim, a comprehensive simulated multi-agent perception\ndataset for V2X-aided autonomous driving. V2X-Sim provides:\n(1) multi-agent sensor recordings from the road-side unit (RSU)\nand multiple vehicles that enable collaborative perception, (2)\nmulti-modality sensor streams that facilitate multi-modality\nperception, and (3) diverse ground truths that support various\nperception tasks. Meanwhile, we build an open-source testbed\nand provide a benchmark for the state-of-the-art collaborative\nperception algorithms on three tasks, including detection, tracking and segmentation. V2X-Sim seeks to stimulate collaborative\nperception research for autonomous driving before realistic\ndatasets become widely available.\n\n\n\n## Dataset\n\nDownload links:\n- Original dataset (you are going to parse this dataset yourself with `create_data.py` scripts for specific tasks): [Google Drive (US)](https://huggingface.co/datasets/ai4ce/V2X-Sim-2.0)  \n- preprocessed datasets for detection and segmentation tasks and model checkpoints: [Google Drive (US)](https://drive.google.com/drive/folders/1NMag-yZSflhNw4y22i8CHTX5l8KDXnNd?usp=sharing)   \n\nYou could find more detailed documents on our [website](https://ai4ce.github.io/V2X-Sim/index.html)!\n\nV2X-Sim follows the same file structure as the [Nuscenes dataset](https://www.nuscenes.org/):\n```\nV2X-Sim\n├── maps # images for the map of one of the towns\n├── sweeps # sensor data\n|   ├── LIDAR_TOP_id_0 # top lidar data for the top camera, agent 0 (RSU)\n|   ├── LIDAR_TOP_id_1 # top lidar data for the top camera, agent 1\n|   ├── LIDAR_TOP_id_2 # top lidar data for the top camera, agent 2\n|   ...\n├── v1.0-mini # metadata\n|   ├── scene.json # metadata for all the scenes\n|   ├── sample.json # metadata for each sample, organized like linked-list\n|   ├── sample_annotation.json # sample annotation metadata for each scene\n|   ...\n```\n\nFor parsed detection and segmentation dataset, the file structure will be:\n```\nV2X-Sim-det / V2X-Sim-seg\n├── train # training data\n|   ├── agent0 # data for RSU\n|   |   ├── 0_0 # scene 0, frame 0\n|   |   ├── 0_1 # scene 0, frame 1\n|   |   |   ...\n|   ├── agent1 # data for agent 1\n|   ...\n|   ├── agent5 # data for agent 5\n├── val # validation data\n├── test # test data\n```\n\n\nhttps://user-images.githubusercontent.com/53892579/180342204-1697f102-5f69-45d1-a62e-9460f4628fb8.mp4\n\nhttps://user-images.githubusercontent.com/53892579/180342351-ef58e302-9bcb-47fa-a80f-1fe49ee80152.mp4\n\nhttps://user-images.githubusercontent.com/53892579/180341986-1389ba9a-2bab-427f-8873-7cd7cba38fbe.mp4\n\n## Requirements\n\nTested with:\n\n- Python 3.7\n- PyTorch 1.8.0\n- Torchvision 0.9.0\n- CUDA 11.2\n\n\n\n## Benchmark\n\nWe implement when2com, who2com, V2VNet, lowerbound and upperbound benchmark experiments on our datasets. You are welcome to go to `README` files in [detection](https://github.com/coperception/coperception/tree/master/tools/det), [segmentation](https://github.com/coperception/coperception/tree/master/tools/seg) and [tracking](https://github.com/coperception/coperception/tree/master/tools/track) to find them.\n\n\n\n## Acknowledgement\n\nWe are very grateful to multiple great opensourced codebases, without which this project would not have been possible:\n\n- [NuSenes-devkit](https://github.com/nutonomy/nuscenes-devkit)\n- [sort](https://github.com/abewley/sort)\n- [TrackEval](https://github.com/JonathonLuiten/TrackEval)\n- [coperception](https://github.com/coperception/coperception)\n\n## Citation\n\nIf you find V2XSIM useful in your research, please cite:\n\n```bibtex\n@article{li2022v2x,\n  title={V2X-Sim: Multi-Agent Collaborative Perception Dataset and Benchmark for Autonomous Driving},\n  author={Li, Yiming and Ma, Dekun and An, Ziyan and Wang, Zixun and Zhong, Yiqi and Chen, Siheng and Feng, Chen},\n  journal={IEEE Robotics and Automation Letters},\n  volume={7},\n  number={4},\n  pages={10914--10921},\n  year={2022},\n  publisher={IEEE}\n}\n```\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fai4ce%2FV2X-Sim","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fai4ce%2FV2X-Sim","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fai4ce%2FV2X-Sim/lists"}